© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8400
    Prev
    Next
    INDEX
    Explanations

    descriptive colors and visual characteristics related to objects and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Colors (often crystalline solids)

    np_acts-logits-general · gemini-2.0-flash

    colors and color names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -1.12
    Personensuche
    -1.11
    AnchorStyles
    -1.00
     InputDecoration
    -0.93
    sizeCache
    -0.90
     الرياضيه
    -0.90
    abestanden
    -0.88
     EconPapers
    -0.87
    RenderAtEndOf
    -0.86
    GEBURTSDATUM
    -0.79
    POSITIVE LOGITS
     color
    0.74
     اللون
    0.64
     colour
    0.64
     رنگ
    0.62
    色的
    0.62
     renk
    0.60
    ish
    0.60
     رنگی
    0.59
     colored
    0.57
     kleur
    0.57
    Activations Density 0.195%

    No Known Activations